Deliberative alignment: reasoning enables safer language models

2024-12-20来源 OpenAI BlogEnglish
Deliberative alignment: reasoning enables safer language models Introducing our new alignment strategy for o1 models, which are directly taught safety specifications and how to reason over them.

原文：https://www.a8q9.cn/en/article/deliberative-alignment-reasoning-enables-safer-language-models-eb1775.html

相关文章